Journalists must be trained in how to recognise and deal with algorithm bias in order to counter the speed and scale at which biased content is being spread. That’s the view of Gemini, the artificial intelligence (AI) conversation tool, which says that the need for such training is “more urgent than ever”.

AI says “the rapid advancement of artificial intelligence and machine learning has led to a significant increase in the use of algorithms in news production” and that “algorithms can introduce bias into news content, which can have serious consequences for both individuals and society.”

Media Helping Media (MHM) asked Gemini how journalists can recognise and deal with algorithm bias. We also asked it to design a one-day training course to equip journalists with the tools they need to tackle the issue.

The following is the text of that conversation, which took place in September 2024. During the conversation Gemini states that while the challenge of bias in news production is not entirely new, the rise of AI has made it more urgent and complex.

AI warns that “journalists and news organisations must adapt to this new reality by developing strategies to mitigate algorithm bias and ensure that the news they produce is fair, accurate, and representative”.

I asked AI the following questions. The answers were immediate. Gemini’s responses are unedited other than to change them from American English to English English  (MHM’s preferred house style).

MHM: What is algorithm bias in news production?

Gemini AI: Algorithm bias in news production refers to the unintentional or intentional bias introduced into news content by the algorithms used to curate, personalise, or generate news. This bias can manifest in various ways, including:

• Selection bias: Algorithms may prioritise certain stories or topics over others, leading to a skewed representation of the news.
• Confirmation bias: Algorithms may reinforce existing beliefs or biases by recommending content that aligns with a user’s preferences.
• Representation bias: Algorithms may underrepresent certain groups or perspectives, leading to a lack of diversity in the news.
• Amplification bias: Algorithms may amplify certain narratives or misinformation, contributing to the spread of false or misleading information.

Factors contributing to algorithm bias:

• Biased data: If the data used to train algorithms is biased, the algorithms will likely produce biased outputs.
• Biased algorithms: The design of algorithms themselves can introduce bias, such as by prioritising certain features or metrics over others.
• Lack of transparency: The lack of transparency in how algorithms work can make it difficult to identify and address bias.

Addressing algorithm bias in news production requires a multi-faceted approach, including:

• Improving data quality: Ensuring that the data used to train algorithms is diverse, representative, and free from bias.
• Designing unbiased algorithms: Developing algorithms that are transparent, accountable, and resistant to bias.
• Promoting transparency: Increasing transparency in how algorithms are used and the decisions they make.
• Human oversight: Ensuring that human editors and journalists play a role in reviewing and curating news content.

By understanding and addressing algorithm bias, news organisations can help to ensure that the news they produce is fair, accurate, and representative.

MHM: How can journalists avoid algorithm bias if they are not in control of the algorithms?

Gemini AI: While journalists may not have direct control over the algorithms used in news production, they can take several steps to mitigate algorithm bias:

1. Be aware of algorithm bias: Journalists should understand the concept of algorithm bias and how it can manifest in news content. This knowledge can help them identify potential biases and take steps to address them.
2. Critically evaluate news sources: Journalists should be sceptical of news stories generated or curated by algorithms. They should carefully evaluate the sources of information and verify the accuracy of the content.
3. Seek diverse sources: Journalists should strive to gather information from a variety of sources, including those that may not be prominently featured in algorithm-driven news feeds. This can help to ensure that the news they report is balanced and representative.
4. Use human judgement: Journalists should rely on their own judgement to assess the quality and relevance of news stories. They should be willing to override algorithmic recommendations if they believe that they are biased or misleading.
5. Advocate for transparency: Journalists can advocate for greater transparency in how algorithms are used in news production. This can help to identify and address biases and ensure that the news is produced in a fair and ethical manner.
6. Collaborate with data scientists: Journalists can collaborate with data scientists to understand how algorithms work and identify potential biases. This can help them to develop strategies for mitigating algorithm bias.

By taking these steps, journalists can help to ensure that the news they report is accurate, balanced, and free from algorithm bias.

MHM: So mitigating algorithm bias is a new task brought about by the advance of AI but should now become a crucial part of a news producer’s job?

Gemini AI: That’s a great observation. While the term ‘algorithm bias’ may be relatively new, the underlying issue of bias in news production has existed for centuries. However, the advent of AI and machine learning has amplified the potential for bias to be introduced into news content at a larger scale and at a faster pace.

Here’s a breakdown of how traditional news production compared to AI-driven news:

Traditional News Production:

• Human curation: News editors and journalists manually select and curate stories based on their judgement and expertise.
• Limited reach: News distribution was primarily through print and broadcast media, limiting the audience and potential for bias.

AI-Driven News Production:

• Algorithmic curation: Algorithms use data to recommend news stories to users, often based on their past behaviour and preferences.
• Vast reach: News can be disseminated instantly to a global audience through digital platforms, increasing the potential impact of bias.

Key differences:

• Scale: AI can process and analyse vast amounts of data, increasing the potential for bias to be introduced at a larger scale.
• Speed: AI can disseminate news at a much faster pace than traditional methods, making it difficult to identify and correct biases before they have a significant impact.
• Personalisation: AI can personalise news content to individual users, potentially reinforcing existing biases and limiting exposure to diverse perspectives.

Therefore, while the challenge of bias in news production is not entirely new, the rise of AI has made it more urgent and complex. Journalists and news organisations must adapt to this new reality by developing strategies to mitigate algorithm bias and ensure that the news they produce is fair, accurate, and representative.

MHM: So would you say that dealing with algorithm bias should now be part of every journalist’s basic training?

Gemini AI: Absolutely. Dealing with algorithm bias should be a fundamental part of every journalist’s training in the digital age. Here’s why:

1. Understanding the problem: Journalists need to understand how algorithms work, how they can introduce bias, and the potential consequences of this bias.
2. Identifying and mitigating bias: Journalists should be able to identify signs of algorithm bias in news content and take steps to mitigate its effects.
3. Evaluating sources: Journalists should be able to critically evaluate the sources of information they rely on, especially those that are generated or curated by algorithms.
4. Promoting diversity and inclusion: Journalists should strive to promote diversity and inclusion in the news they report, by seeking out a variety of sources and avoiding algorithmic biases that may underrepresent certain groups or perspectives.
5. Advocating for transparency: Journalists can advocate for greater transparency in how algorithms are used in news production, which can help to identify and address biases.

By incorporating training on algorithm bias into journalism programmes, we can equip journalists with the skills and knowledge they need to produce fair, accurate, and representative news in the digital age.

MHM: Could you suggest the outline for a one-day training course for journalists who want to understand and tackle algorithm bias?

Gemini AI: Absolutely. Here is an outline for a one-day training course on algorithm bias for journalists

Morning Session: Understanding Algorithm Bias

• Introduction to algorithms in news production:
  • How algorithms are used in news curation, personalisation, and generation
  • Common types of algorithms (e.g., recommendation engines, natural language processing)
• Understanding bias:
  • Defining bias and its different forms (e.g., selection bias, confirmation bias, representation bias)
  • The impact of bias on news quality and credibility
• Sources of algorithm bias:
  • Biased data
  • Biased algorithms
  • Lack of transparency
• Case studies of algorithm bias in news:
  • Real-world examples of how algorithm bias has affected news coverage
  • Lessons learned from these cases

Afternoon Session: Tackling Algorithm Bias

• Identifying algorithm bias in news content:
  • Recognising signs of bias in news stories generated or curated by algorithms
  • Tools and techniques for detecting bias
• Mitigating algorithm bias:
  • Strategies for reducing the impact of bias in news production
  • Best practices for data collection and curation
  • Designing unbiased algorithms
  • Promoting transparency and accountability
• Human oversight and editorial judgement:
  • The role of human editors and journalists in ensuring the quality and fairness of news content
  • Balancing algorithmic recommendations with human expertise
• Advocating for change:
  • How journalists can advocate for greater transparency and accountability in the use of algorithms in news production
  • Engaging with news organisations and policymakers to address algorithm bias

Workshop Activities:

• Group discussions: Facilitated discussions on specific case studies and challenges related to algorithm bias
• Hands-on exercises: Practical exercises to identify and analyse algorithm bias in news content
• Role-playing scenarios: Simulations of real-world situations where journalists need to deal with algorithm bias
• Guest speakers: Invited experts from the fields of journalism, technology, and ethics to share their insights and experiences

Additional Considerations:

• Tailoring the course: The content of the course can be tailored to the specific needs and interests of the participating journalists.
• Online or in-person: The training can be conducted either in-person or online, depending on the preferences of the participants and the resources available.
• Continuous learning: Encourage participants to continue learning about algorithm bias and best practices for mitigating its effects through ongoing professional development.

MHM: And what sources would you recommend for supporting the course on algorithm bias which you have just outlined?

Gemini AI: Recommended sources for a course on algorithm bias in news production include:

Books:

• Weapons of Math Destruction by Cathy O’Neil: This book explores how algorithms can perpetuate inequality and discrimination.
• Automating Inequality by Virginia Eubanks: This book examines the ways in which algorithms are used to reinforce existing social and economic inequalities.
• Algorithms of Oppression by Safiya Umoja Noble: This book focuses on the racial bias inherent in many algorithms and their impact on marginalised communities.
• The Algorithm: The Ultimate Power by Brian Christian and Tom Griffiths: This book provides a general introduction to algorithms and their applications.

Articles and Papers:

• Journal of Computer-Mediated Communication: This journal publishes research on the intersection of technology and communication, including studies on algorithm bias.
• Digital Journalism & Ethics: This journal focuses on ethical issues in digital journalism, including the use of algorithms.
• Pew Research Center: This organisation conducts research on a variety of topics related to technology and society, including algorithm bias.
• MIT Technology Review: This publication covers emerging technologies and their societal implications, including the impact of algorithms.

Online Resources:

• AlgorithmWatch: This non-profit organisation works to increase transparency and accountability in the use of algorithms.
• Open Rights Group: This organisation campaigns for digital rights, including the right to be free from algorithmic discrimination.
• Mozilla Foundation: This foundation is dedicated to building a healthy internet, including efforts to address algorithm bias.
• The Markup: This investigative journalism outlet focuses on the impact of technology on society, including the role of algorithms.

Case Studies:

• The Facebook Cambridge Analytica scandal: This case highlights the potential for algorithms to be used to manipulate public opinion.
• The YouTube algorithm and the spread of misinformation: This case demonstrates how algorithms can amplify harmful content.
• The use of algorithms in criminal justice: This case raises concerns about the potential for algorithms to perpetuate racial bias.

By incorporating these sources into your training course, you can provide participants with a comprehensive understanding of algorithm bias and the tools they need to address it.

MHM: Would you say that the need for journalists to be trained in dealing with algorithm bias is urgent?

Gemini AI: Absolutely. The need for journalists to be trained in dealing with algorithm bias is more urgent than ever. The rapid advancement of artificial intelligence and machine learning has led to a significant increase in the use of algorithms in news production. These algorithms can introduce bias into news content, which can have serious consequences for both individuals and society.

Here are some reasons why this training is urgent:

• Increasing reliance on algorithms: News organisations are increasingly relying on algorithms to curate, personalise, and generate news content. This means that the potential for algorithm bias to impact news coverage is growing.
• The potential for harm: Algorithm bias can lead to the spread of misinformation, the amplification of harmful stereotypes, and the underrepresentation of certain groups or perspectives. This can have serious consequences for individuals and society.
• The need for accountability: Journalists have a responsibility to ensure that the news they report is accurate, fair, and unbiased. This includes understanding and addressing the potential for algorithm bias.

By training journalists in how to identify and mitigate algorithm bias, we can help to ensure that the news we consume is reliable and trustworthy.

MHM’s conclusion

The fact that AI is warning that journalists need to be trained in recognising and dealing with algorithm bias suggests that human judgement, journalistic ethics and editorial values are crucial in a world where artificial intelligence and machine learning is crafting so much content. As Gemini says in the interview above, “the underlying issue of bias in news production has existed for centuries. However, the advent of AI and machine learning has amplified the potential for bias to be introduced into news content at a larger scale and at a faster pace.”

The post Dealing with algorithm bias in news first appeared on Media Helping Media.

Have you ever chaired a news meeting surrounded by blank faces with no story ideas? Well, with AI that experience could be a thing of the past. Simply asking AI what the top stories of the day are and then asking for suggestions for news angles could result in far too many stories to cover. But, better too many than too few.

Media Helping Media (MHM) tested Google’s Gemini AI conversation tool by asking it to list the top five news stories for Thursday 26 September 2024. I then asked it to suggest how those stories should be treated and challenged Gemini AI to dig deeper into each story idea and come up with interesting angles.

The results were impressive and the answers were immediate. Gemini’s responses to my questions are unedited other than to change them from American English to English English  (MHM’s preferred house style).

MHM: What are the current top news stories in the world?

Gemini AI: Here are some of the top news stories in the world as of September 26, 2024:

• Israel-Hezbollah Conflict: The ongoing conflict between Israel and Hezbollah in Lebanon continues to dominate headlines. There have been numerous attacks and counterattacks, and the situation remains tense.
• Russia-Ukraine War: The war in Ukraine is still ongoing, with both sides reporting casualties and territorial gains. Diplomatic efforts to find a peaceful resolution have so far been unsuccessful.
• Tropical Storm Helene: Tropical Storm Helene is expected to make landfall in the United States, and authorities are urging residents to prepare for potential flooding and power outages.
• New Mpox Strain: India has reported its first case of a new, fast-spreading strain of mpox. The health ministry is monitoring the situation closely and urging people to be vigilant.
• New York Mayor Eric Adams Indicted: New York City Mayor Eric Adams has been indicted on corruption charges. The investigation is ongoing, and Adams has denied any wrongdoing.

These are just a few of the top news stories in the world at the moment. Please note that the news landscape is constantly changing, so it is important to stay informed by following reputable news sources.

MHM: What angles could we explore on those top five news stories taken one-by-one?

Gemini AI: In order to analyse the top news stories one by one you should look at the following areas.

1. Israel-Hezbollah Conflict

• Humanitarian Crisis: Explore the impact of the conflict on civilians, including displacement, injuries, and deaths.
• Regional Implications: Analyse how the conflict is affecting neighbouring countries and the wider Middle East.
• Diplomatic Efforts: Examine the role of international organisations and individual countries in attempting to broker a ceasefire or peace agreement.
• Military Strategies: Discuss the tactics and weapons being used by both sides, and analyse their effectiveness.

2. Russia-Ukraine War

• Economic Impact: Explore the effects of the war on the global economy, including rising energy prices and disruptions to supply chains.
• Refugee Crisis: Examine the situation of millions of Ukrainians who have fled the country, and the challenges they face in finding safety and support.
• War Crimes: Investigate allegations of war crimes committed by both sides, and the efforts to hold perpetrators accountable.
• Prospects for Peace: Discuss the potential for a negotiated settlement, and the obstacles that must be overcome.

3. Tropical Storm Helene

• Preparations and Response: Examine the steps taken by local and national authorities to prepare for and respond to the storm, including evacuation orders, emergency shelters, and disaster relief efforts.
• Environmental Impact: Analyse the potential effects of the storm on the environment, such as flooding, erosion, and damage to ecosystems.
• Economic Impact: Assess the economic costs of the storm, including property damage, business disruptions, and insurance claims.
• Climate Change Connection: Discuss the relationship between the storm and climate change, and the implications for future extreme weather events.

4. New Mpox Strain

• Public Health Response: Examine the measures being taken by health authorities to contain the spread of the new strain, such as contact tracing, vaccination campaigns, and public education efforts.
• Global Implications: Assess the potential for the new strain to spread to other parts of the world, and the risks it poses to public health.
• Research and Development: Discuss the need for further research into the new strain, including its characteristics, transmissibility, and potential treatments.
• Social and Economic Impacts: Explore the social and economic consequences of the outbreak, such as stigma, discrimination, and disruptions to daily life.

5. New York Mayor Eric Adams Indicted

• Legal Proceedings: Follow the legal proceedings, including the charges filed, the evidence presented, and the potential outcomes.
• Political Implications: Analyse the impact of the indictment on the mayor’s political career, his relationship with the public, and the city’s governance.
• Corruption in Politics: Discuss the broader issue of corruption in politics, and the measures that can be taken to prevent it.
• Public Opinion: Examine public opinion on the indictment and the mayor’s handling of the situation.

MHM: Can you suggest interesting ways to explore those news angles?

Gemini AI: To present news angles in a distinctive manner, consider these approaches:

1. Humanise the Story:

• Focus on individuals: Highlight personal experiences and anecdotes to connect readers emotionally.
• Use storytelling: Craft narratives that draw readers into the story.
• Emphasise the human cost: Explore the impact of events on individuals and communities.

2. Leverage Unexpected Connections:

• Identify surprising links: Find connections between seemingly unrelated topics.
• Use analogies: Draw parallels to familiar concepts to make complex issues more understandable.
• Explore counterintuitive perspectives: Challenge conventional wisdom and offer alternative viewpoints.

3. Utilise Visual Storytelling:

• Create compelling visuals: Use infographics, charts, and images to illustrate data and concepts.
• Employ multimedia: Incorporate videos, audio clips, and interactive elements to enhance engagement.
• Tell stories through visuals: Use images and graphics to convey narratives without words.

4. Explore the Historical Context:

• Examine past events: Compare current events to similar situations in the past.
• Identify patterns and trends: Analyse historical data to identify recurring themes.
• Provide historical context: Explain the significance of events within a broader historical framework.

5. Offer a Unique Perspective:

• Consider different viewpoints: Explore the issue from multiple angles.
• Interview experts: Seek out insights from experts who can provide unique perspectives.
• Challenge assumptions: Question commonly held beliefs and offer alternative interpretations.

6. Focus on the Unexpected:

• Highlight unusual details: Draw attention to unexpected or surprising aspects of the story.
• Explore the unexpected consequences: Examine unintended or unforeseen outcomes of events.
• Offer a fresh perspective: Present the story in a way that readers haven’t seen before.

7. Incorporate Humor or Satire:

• Use humour to lighten the mood: Employ humour to make complex topics more accessible.
• Utilise satire to critique: Satirize issues or individuals to highlight flaws or absurdities.
• Balance humour with seriousness: Ensure that humour doesn’t undermine the importance of the topic.

By combining these techniques, you can create news angles that are informative, engaging, and memorable. Would you like to explore a specific news topic and brainstorm potential angles?

MHM: Let’s brainstorm potential news angles together.

Gemini AI: Absolutely! Let’s choose a news topic together. To give you some ideas, here are a few current events you could consider:

• Artificial Intelligence: The rapid development of AI, its potential benefits and risks, and its impact on society.
• Climate Change: The increasing frequency and severity of extreme weather events, the transition to renewable energy, and international efforts to mitigate climate change.
• Social Justice: Issues related to equality, diversity, and inclusion, including racial justice, gender equality, and economic inequality.
• Healthcare: The rising cost of healthcare, access to medical care, and advancements in medical technology.
• Technology: The latest developments in technology, such as virtual reality, augmented reality, and the Internet of Things.

Which topic would you like to explore?

MHM: Let’s explore climate change.

Gemini AI: Climate change is a vast and complex topic with endless angles to explore. Here are a few unique approaches you could consider:

Human-Centred Stories:

• Personal Narratives: Interview individuals who have been directly affected by climate change, such as farmers experiencing crop failures or coastal residents facing rising sea levels.
• Community Resilience: Highlight communities that have successfully adapted to climate change, focusing on their innovative solutions and resilience.
• Health Impacts: Explore the health consequences of climate change, including heat-related illnesses, respiratory problems, and the spread of diseases.

Unexpected Connections:

• Cultural Impacts: Examine how climate change is affecting cultural traditions, heritage sites, and indigenous communities.
• Economic Implications: Explore the economic costs of climate change, from lost productivity to increased insurance premiums.
• Technological Advancements: Highlight emerging technologies that could help mitigate climate change, such as renewable energy sources, carbon capture, and climate-resilient infrastructure.

Visual Storytelling:

• Time-Lapse Photography: Use time-lapse photography to show the dramatic changes in glaciers, forests, or coastlines over time.
• Data Visualization: Create infographics or interactive maps to illustrate climate data, such as temperature trends, sea-level rise, or extreme weather events.
• Virtual Reality Experiences: Immerse readers in virtual reality simulations of climate change scenarios, such as flooding or extreme heatwaves.

Historical Perspective:

• Climate History: Explore past climate events and their impact on civilizations.
• Historical Parallels: Compare current climate challenges to historical events, such as the Dust Bowl or the Little Ice Age.
• Lessons from the Past: Analyse past responses to climate change and identify successful strategies.

Unique Perspectives:

• Animal Impacts: Examine how climate change is affecting wildlife, ecosystems, and biodiversity.
• Ethical Considerations: Explore the ethical implications of climate change, such as the distribution of resources and intergenerational justice.
• Art and Culture: Highlight how artists and cultural figures are responding to climate change through their work.

Would you like to explore one of these angles in more detail, or do you have another idea in mind?

MHM: Yes please let’s explore the animal impacts angle.

Gemini AI: This topic offers a unique perspective on climate change, as it highlights the direct and often devastating effects on wildlife. Here are some potential sub-angles you could consider:

• Habitat Loss: Examine how climate change is leading to the loss of habitats, such as forests, wetlands, and coral reefs, and the subsequent decline of species that rely on these environments.
• Range Shifts: Explore how species are shifting their geographic ranges in response to changing temperatures and precipitation patterns, leading to competition with other species and potential extinction.
• Behavioural Changes: Investigate how climate change is altering the behaviours of animals, such as migration patterns, breeding seasons, and foraging habits.
• Disease Outbreaks: Discuss how climate change is contributing to the spread of diseases among wildlife, such as zoonotic diseases that can also infect humans.
• Conservation Efforts: Highlight conservation initiatives aimed at protecting wildlife from the impacts of climate change, including habitat restoration, assisted migration, and captive breeding programs.

Would you like to focus on a specific aspect of animal impacts, or do you have other questions about this topic?

MHM: Yes please, let’s focus on habitat loss as a sub-angle.

Gemini AI: Habitat loss is a major driver of species extinction, and climate change is exacerbating this problem. Here are some potential story ideas:

• Case Studies: Examine specific examples of habitat loss due to climate change, such as the decline of polar bears in the Arctic or the loss of coral reefs in tropical oceans.
• The Role of Extreme Weather Events: Explore how extreme weather events, such as wildfires, floods, and droughts, are destroying habitats and displacing wildlife.
• The Impact on Endangered Species: Investigate how habitat loss is particularly threatening to endangered species, as they often have limited geographic ranges and specialised requirements.
• Conservation Efforts: Highlight conservation initiatives aimed at protecting and restoring habitats, such as reforestation programs, wetland restoration, and the creation of wildlife corridors.
• The Human Cost: Discuss the human consequences of habitat loss, including impacts on food security, water resources, and cultural heritage.

Would you like to explore any of these ideas in more detail, or do you have another angle in mind?

MHM: Yes, perhaps the human cost.

Gemini AI: The Human Cost of Habitat Loss is a powerful and relevant angle that can highlight the direct and indirect consequences of climate change on human communities. Here are some potential story ideas:

• Food Security: Examine how habitat loss is affecting food production, particularly in regions that rely on agriculture and fishing. Explore the impact on local communities and food prices.
• Water Resources: Discuss how habitat loss is affecting water quality and availability, particularly in areas where forests and wetlands play a crucial role in water filtration and regulation.
• Health Impacts: Explore the health consequences of habitat loss, such as increased exposure to air pollution, waterborne diseases, and vector-borne illnesses.
• Cultural Heritage: Examine how habitat loss is affecting cultural heritage sites, such as ancient forests, sacred landscapes, and traditional fishing grounds.
• Economic Impacts: Discuss the economic costs of habitat loss, including lost livelihoods, increased disaster relief expenses, and reduced tourism revenue.

Would you like to explore any of these ideas in more detail, or do you have another angle in mind?

MHM: Yes please, let’s explore the health impacts.

Gemini AI: The Health Impacts of Habitat Loss is a critical and often overlooked aspect of climate change. Here are some potential story ideas:

• Air Quality: Examine how habitat loss, particularly deforestation, is contributing to air pollution, which can lead to respiratory problems, heart disease, and other health issues.
• Waterborne Diseases: Discuss how habitat loss, such as the degradation of wetlands, is affecting water quality and increasing the risk of waterborne diseases, such as cholera, typhoid, and dysentery.
• Vector-Borne Diseases: Explore how habitat loss is creating conditions that favour the spread of vector-borne diseases, such as malaria, dengue fever, and Zika virus, by altering the habitat of mosquitoes and other disease-carrying insects.
• Mental Health: Investigate the mental health impacts of habitat loss, including stress, anxiety, and depression, particularly in communities that rely on natural resources for their livelihoods and well-being.
• Disasters and Health: Examine how habitat loss is increasing the vulnerability of communities to natural disasters, such as floods, wildfires, and hurricanes, which can have severe health consequences.

Would you like to explore any of these ideas in more detail, or do you have another angle in mind?

MHM: Yes, let’s talk more about ‘vector-borne diseases.

Gemini AI: Vector-borne diseases are a significant public health concern, and habitat loss plays a crucial role in their transmission. Here are some potential story ideas:

• Habitat Alteration: Examine how habitat alteration, such as deforestation and urbanisation, is creating new breeding grounds for mosquitoes and other disease-carrying insects.
• Climate Change and Vector Ecology: Explore how climate change is affecting the geographic range and activity of vectors, allowing them to spread diseases to new areas.
• Disease Surveillance: Investigate the challenges of disease surveillance in areas affected by habitat loss, as changes in ecosystems can make it difficult to track and control outbreaks.
• Community Health Initiatives: Highlight community-based programs aimed at preventing and controlling vector-borne diseases, such as mosquito control measures and health education campaigns.
• Global Health Implications: Discuss the global health implications of vector-borne diseases linked to habitat loss, including the potential for pandemics and the economic burden on affected countries.

Would you like to explore any of these ideas in more detail, or do you have another angle in mind?

MHM: Yes please, let’s discuss disease surveillance.

Gemini AI: Disease surveillance is essential for tracking and controlling outbreaks, particularly in areas affected by habitat loss. Here are some potential story ideas:

• Challenges in Remote Areas: Examine the challenges of disease surveillance in remote or inaccessible areas, where habitat loss may have occurred and where access to healthcare and public health services is limited.
• Community-Based Surveillance: Highlight community-based disease surveillance initiatives that involve local residents in monitoring for symptoms and reporting potential cases.
• Early Warning Systems: Discuss the development and implementation of early warning systems to detect and respond to disease outbreaks in areas affected by habitat loss.
• Data Analysis and Modelling: Explore the use of data analysis and modelling techniques to predict the spread of diseases based on factors such as habitat loss, climate change, and human population density.
• International Collaboration: Examine the importance of international collaboration in disease surveillance, particularly for diseases that can spread across borders.

Would you like to explore any of these ideas in more detail, or do you have another angle in mind?

MHM: Yes please, it would be good to look into early warning systems.

Gemini AI: Early warning systems are crucial for detecting and responding to disease outbreaks, especially in areas affected by habitat loss. Here are some potential story ideas:

• Technology and Innovation: Highlight the latest technological advancements in early warning systems, such as satellite imagery, remote sensing, and data analytics.
• Community-Based Early Warning Systems: Explore the role of community-based early warning systems, which rely on local residents to report unusual symptoms or unusual animal behaviour.
• Integration of Data: Discuss the importance of integrating data from various sources, including health records, environmental data, and climate models, to improve the accuracy and effectiveness of early warning systems.
• Case Studies: Examine specific case studies of early warning systems that have successfully prevented or mitigated disease outbreaks in areas affected by habitat loss.
• Challenges and Limitations: Address the challenges and limitations of early warning systems, such as the need for adequate funding, trained personnel, and reliable data.

Would you like to explore any of these ideas in more detail, or do you have another angle in mind?

MHM: How do I get hold of the data you mention?

Gemini AI: Data is a crucial component of effective disease surveillance and habitat loss research. Here are some potential sources:

Government Agencies and Organisations:

• National Health Services: Most countries have national health services that collect and analyse health data, including disease surveillance data.
• Environmental Protection Agencies: Environmental protection agencies often collect data on habitat loss, land use changes, and climate factors.
• Research Institutes: Government-funded research institutes may conduct studies on disease surveillance, habitat loss, and their interactions.

International Organisations:

• World Health Organization (WHO): The WHO collects and analyses health data from around the world, including disease surveillance data.
• United Nations Environment Programme (UNEP): The UNEP monitors environmental issues, including habitat loss and biodiversity.
• Intergovernmental Panel on Climate Change (IPCC): The IPCC provides comprehensive assessments of climate change, including its impacts on ecosystems and human health.

Academic Institutions:

• Universities and Research Centres: Many universities and research centres conduct studies on disease surveillance, habitat loss, and their interactions. They may publish their findings in academic journals or make their data available through data repositories.

Data Repositories:

• Government Data Portals: Many governments have data portals where they make public data available.
• Academic Data Repositories: Academic institutions often maintain data repositories where researchers can share and access data.
• International Data Repositories: International organisations may also maintain data repositories that are accessible to researchers.

Remote Sensing Data:

• Satellite Imagery: Satellite imagery can provide valuable data on land use changes, deforestation, and habitat loss.
• Remote Sensing Platforms: There are various remote sensing platforms that provide data, such as NASA’s Earth Observatory and the European Space Agency’s Copernicus program.

When searching for data, be sure to consider the following factors:

• Data Quality: Ensure that the data is reliable and accurate.
• Data Format: Make sure the data is in a format that you can use (e.g., CSV, JSON, GIS).
• Data Access Restrictions: Some data may have restrictions on access or use.

Would you like me to help you find specific data sources for a particular topic?

MHM’s conclusion

AI provided enough news story ideas in a two-minute real-time conversation to keep a newsroom busy for a year. What was interesting was that AI seemed to enjoy brainstorming. It started prompting me to engage further either by asking more on the topic we were discussing or offering to explore another angle. It almost felt like I was having a text conversation with a real person about topics about which they were extremely well informed.

The post Hey AI, what’s on the news agenda today? first appeared on Media Helping Media.

Imagine the scene. You are a journalist covering a story on your own. You need someone to bounce ideas off in order to make sure you cover all angles. But nobody is available. Instead you turn to artificial intelligence (AI) on your mobile phone for instant story development ideas. 

Would the results be any good? Would AI come up with the quality of editorial brainstorming that colleagues back in the newsroom could offer? Media Helping Media (MHM) put Gemini, Google’s AI conversation tool, to the test.  

Gemini’s responses, and my follow-up questions (in large bold headings) are reproduced below. After each answer from Gemini I asked it to expand on points it had made in the previous answer. The conversation took place in September 2024.

I started by creating a fictitious scenario. I told Gemini AI that I am a journalist covering a protest at a refugee camp where asylum seekers are demonstrating about delays in their claims being processed. 

I then asked AI the following questions. The answers were immediate. Gemini’s responses are unedited other than to change them from American English to English English  (MHM’s preferred house style).

MHM: Apart from reporting on the demonstration, what other related news angles should I cover?

Gemini AI: Here are some additional news angles you could consider covering, beyond the immediate demonstration:

Human Interest Stories:

• Individual Refugee Stories: Interview refugees about their personal journeys, hardships, and hopes.
• Community Impact: Explore how the refugee camp is affecting the local community, including potential tensions or positive interactions.

Policy and Government Response:

• Processing Delays: Investigate the reasons for the delays in processing asylum claims, including any bureaucratic hurdles or political pressures.
• Government Response: Examine the government’s response to the protest and any potential changes to asylum policies or procedures.
• International Comparisons: Compare the situation in the UK with other countries that have similar refugee populations.

Living Conditions in the Camp:

• Basic Needs: Assess whether refugees have access to adequate food, shelter, healthcare, and education.
• Security Concerns: Report on any safety issues or concerns within the camp, such as crime or violence.

Legal and Ethical Issues:

• Human Rights: Examine whether the treatment of refugees aligns with international human rights standards.
• Legal Challenges: Explore any legal challenges refugees or their representatives are pursuing to expedite the processing of their claims.

Economic Impact:

• Job Market: Investigate the potential economic impact of refugees on the local job market, both positive and negative.
• Integration Efforts: Report on government or NGO initiatives to help refugees integrate into the local community.

By exploring these additional angles, you can provide a more comprehensive and nuanced understanding of the situation at the refugee camp and its broader implications.

MHM: Could you expand on the ‘Human Interest Stories’ angle please?

Gemini AI: Human interest stories can provide a powerful and personal lens through which to understand the experiences of refugees. Here are some specific avenues you could explore:

Individual Refugee Narratives:

• Personal Journeys: Delve into the individual experiences of refugees, from their home countries to their escape and arrival at the camp.
• Challenges and Hopes: Focus on the specific challenges refugees face, such as language barriers, cultural differences, or separation from loved ones. Also, explore their hopes and dreams for the future.
• Coping Mechanisms: Understand how refugees are coping with the stress and trauma of their experiences.

Community Building:

• Social Networks: Explore how refugees are forming social networks and communities within the camp.
• Cultural Exchange: Highlight instances of cultural exchange or collaboration between refugees from different backgrounds.
• Support Systems: Identify any support systems or networks that are helping refugees to navigate their new environment.

Children and Families:

• Education: Focus on the educational needs of refugee children and any challenges they may face in accessing education.
• Family Dynamics: Explore how families are coping with the challenges of displacement and the uncertainty of their future.
• Child Protection: Address any concerns related to child protection or exploitation within the refugee camp.

Inspiring Stories:

• Overcoming Adversity: Share stories of refugees who have overcome significant challenges and achieved positive outcomes.
• Acts of Kindness: Highlight instances of kindness, compassion, or resilience within the refugee community.

By focusing on these human interest angles, you can help to humanise the refugee experience and foster empathy and understanding among your audience.

MHM: Could you expand on the ‘Policy and Government Response’ angle please?

Gemini AI: When exploring the policy and government response angle, consider these key areas:

Asylum Policy:

• Current Regulations: Examine the specific regulations governing asylum claims in the UK, including eligibility criteria, processing procedures, and potential grounds for refusal.
• Policy Changes: Investigate any recent or proposed changes to asylum policy, and their potential impact on refugees.
• International Comparisons: Compare UK asylum policies with those of other European countries or countries with similar refugee populations.

Government Response to the Protest:

• Official Statements: Analyse official statements from government officials regarding the protest and their commitment to addressing the concerns of refugees.
• Actions Taken: Evaluate any specific actions taken by the government in response to the protest, such as increased staffing for asylum processing or improved living conditions in refugee camps.
• Public Perception: Assess public opinion on the government’s response to the protest and any potential political pressure.

Bureaucratic Hurdles:

• Processing Delays: Investigate the specific reasons for delays in processing asylum claims, including any bureaucratic bottlenecks or administrative inefficiencies.
• Backlogs: Assess the extent of any backlogs in the asylum system and the government’s efforts to address them.
• Resource Allocation: Examine the allocation of resources to asylum processing and whether there is sufficient funding to meet the demand.

Ethical Considerations:

• Human Rights Standards: Evaluate whether the government’s response to the protest and its asylum policies align with international human rights standards.
• Compassionate Treatment: Consider whether the government is demonstrating compassion and respect for the rights of refugees.

By exploring these aspects, you can provide a comprehensive analysis of the government’s role in shaping the experiences of refugees and the effectiveness of its policies in addressing their needs.

MHM: Could you expand on the ‘Living Conditions in the Camp’ angle please?

Gemini AI: When exploring the living conditions in the refugee camp, consider these key areas:

Basic Needs:

• Shelter: Assess the quality and adequacy of the housing provided to refugees, including any issues with sanitation, safety, or privacy.
• Food: Evaluate the availability, quality, and quantity of food provided to refugees, and any concerns about nutritional deficiencies.
• Healthcare: Examine the accessibility, quality, and adequacy of healthcare services within the camp, including mental health support.
• Education: Assess the availability and quality of educational opportunities for refugee children and adults, including language classes and vocational training.

Safety and Security:

• Crime: Investigate any incidents of crime or violence within the camp, including theft, assault, or sexual harassment.
• Security Measures: Evaluate the effectiveness of security measures in place to protect refugees, such as fencing, surveillance, and patrolling.
• Vulnerable Groups: Identify any particularly vulnerable groups within the camp, such as women, children, or individuals with disabilities, and assess their specific needs and challenges.

Sanitation and Hygiene:

• Waste Management: Examine the systems in place for waste management and disposal, and any concerns about sanitation or hygiene.
• Water Supply: Assess the quality and availability of potable water, and any issues with water scarcity or contamination.
• Hygiene Facilities: Evaluate the adequacy of sanitation facilities, such as toilets, showers, and laundry facilities.

Community Infrastructure:

• Recreational Facilities: Explore the availability of recreational facilities, such as playgrounds, sports fields, or community centres.
• Community Spaces: Assess the availability of community spaces for refugees to gather, socialise, and participate in cultural activities.
• Services: Identify any essential services available within the camp, such as shops, post offices, or transportation options.

By exploring these aspects, you can provide a comprehensive picture of the living conditions faced by refugees within the camp and identify any areas where improvements are needed.

MHM: Could you expand on the ‘Legal and Ethical Issues’ angle please?

Gemini AI: When exploring the legal and ethical issues surrounding refugee camps, consider these key areas:

Human Rights:

• International Law: Examine how the treatment of refugees aligns with international human rights law, such as the Universal Declaration of Human Rights and the Refugee Convention.
• Fundamental Rights: Assess whether refugees are enjoying their fundamental rights, including the rights to life, liberty, security of person, and freedom from discrimination.
• Detention: If refugees are detained, examine the legality and conditions of their detention, ensuring they comply with international standards.

Legal Challenges:

• Asylum Claims: Investigate any legal challenges refugees or their representatives are pursuing to expedite the processing of their asylum claims or to challenge denials.
• Access to Justice: Assess whether refugees have adequate access to legal assistance and representation in pursuing their rights.
• Due Process: Ensure that refugees are afforded due process in all legal proceedings, including the right to a fair hearing and the right to appeal decisions.

Ethical Considerations:

• Compassion and Respect: Evaluate whether refugees are being treated with compassion and respect, regardless of their circumstances.
• Vulnerable Groups: Identify any particularly vulnerable groups within the camp, such as women, children, or individuals with disabilities, and assess whether their specific needs and rights are being adequately protected.
• Accountability: Examine the mechanisms in place for ensuring accountability for any human rights violations or abuses that may occur within the camp.

By exploring these aspects, you can provide a comprehensive analysis of the legal and ethical framework governing the treatment of refugees and identify any areas where improvements are needed.

MHM: Could you expand on the ‘Economic Impact’ angle please?

Gemini AI: When exploring the economic impact of refugee camps, consider these key areas:

Local Economy:

• Job Market: Analyse the potential impact of refugees on the local job market, both positive and negative. This may include their potential to fill labour shortages or compete for jobs with local residents.
• Consumer Spending: Assess the potential economic benefits of refugees as consumers, including their spending on goods and services within the local community.
• Entrepreneurship: Identify any entrepreneurial activities or businesses launched by refugees within the camp or the surrounding area.

Government Services:

• Cost of Services: Evaluate the costs to the government of providing services to refugees, such as housing, healthcare, and education.
• Resource Allocation: Assess whether the government is allocating sufficient resources to support refugees and mitigate any negative economic impacts.
• Long-Term Costs: Consider the potential long-term economic costs associated with refugee resettlement, including the costs of integration and social services.

Integration Efforts:

• Language Training: Examine the availability and effectiveness of language training programs to help refugees learn the local language and improve their employability.
• Vocational Training: Assess the availability and quality of vocational training programs to equip refugees with the skills needed to find employment.
• Integration Initiatives: Evaluate the effectiveness of government or NGO initiatives to help refugees integrate into the local community and participate fully in economic life.

By exploring these aspects, you can provide a comprehensive analysis of the economic implications of refugee camps and identify any potential opportunities or challenges associated with refugee resettlement.

MHM: Are there any other related news angles that you have not mentioned that would add value to the story and better inform the audience?

Gemini AI: Here are some more potential news angles that could add value to your story:

Health and Well-being:

• Mental Health: Explore the mental health challenges faced by refugees, including PTSD, depression, and anxiety.
• Physical Health: Assess the physical health of refugees, including any common illnesses or health conditions.
• Access to Healthcare: Examine the availability and quality of healthcare services within the camp, and any barriers to access.

Education and Skills Development:

• Educational Opportunities: Investigate the educational opportunities available to refugee children and adults, including formal schooling and vocational training.
• Language Barriers: Explore the challenges faced by refugees in learning the local language and accessing education.
• Skills Development: Identify any programs or initiatives aimed at developing the skills and employability of refugees.

Cultural and Social Integration:

• Cultural Preservation: Explore how refugees are preserving their cultural heritage and traditions within the camp.
• Intercultural Dialogue: Examine opportunities for intercultural dialogue and exchange between refugees and the local community.
• Social Integration: Assess the challenges and opportunities for refugees to integrate into the local society and build social connections.

Media Representation:

• Media Portrayal: Examine how refugees are portrayed in the media, and any stereotypes or misconceptions that may exist.
• Media Access: Assess the access of refugees to information and media outlets, and any challenges they may face in accessing accurate and unbiased information.

Future Prospects:

• Resettlement: Explore the prospects for refugees to be resettled to a third country and the challenges associated with this process.
• Self-Reliance: Examine any initiatives or programs aimed at empowering refugees to become self-reliant and contribute to their own well-being.
• Long-Term Goals: Explore the long-term goals and aspirations of refugees for their future, including their hopes for their children and their communities.

By exploring these additional angles, you can provide a more comprehensive and nuanced understanding of the situation at the refugee camp and its broader implications.

MHM’s conclusion

AI can offer real-time editorial brainstorming for the solo journalist who needs to bounce ideas around in order to explore all possible story angles. It does this in an instant, enabling the journalist to focus their news-gathering efforts on areas that will enhance their news reporting.

The post Hey AI, I’m out on a story – can you help? first appeared on Media Helping Media.

What are the benefits and dangers of using artificial intelligence (AI) in the news production process? We interviewed Gemini, Google’s AI conversation tool, to try to find out how AI views its relationship with journalism.

Benefits listed by AI include generating routine data-driven news reports in order to free journalists to apply “critical thinking and judgement” and “empathy and understanding”, as well as highlighting important news angles that could be missed by journalists.

Dangers include “algorithmic bias” where AI perpetuates “existing biases present in the data they are trained on”, creating “deepfakes and manipulated content”, and “privacy concerns” related to data retrieval, analysis and use.

The interview with AI took place in September 2024 and is reproduced below. Gemini’s responses are unedited other than to change them from American English to English English (MHM’s preferred house style). MHM’s questions are in large bold text.

MHM: How can AI assist journalism?

Gemini AI: AI is revolutionising the way journalism is produced, offering a range of benefits that can enhance efficiency, accuracy, and accessibility. Here are some key ways AI is assisting journalism:

1. Data analysis and visualisation:

• Data-driven stories: AI can process vast amounts of data to identify trends, patterns, and anomalies that would be difficult for humans to spot. This enables journalists to create data-driven stories that are more informative and impactful.
• Interactive visualisations: AI can generate interactive visualisations, such as charts, graphs, and maps, to make complex data more understandable and engaging for readers.

2. Content creation and automation:

• Automated reporting: AI can generate routine news reports, such as sports scores, weather updates, and financial news, freeing up journalists to focus on more complex and in-depth stories.
• Content personalisation: AI can personalise news content based on individual reader preferences, ensuring that they receive the most relevant and interesting information.

3. Fact-checking and verification:

• Fake news detection: AI can help identify and debunk fake news by analysing the content, source, and context of information.
• Source verification: AI can verify the credibility of sources by checking their reputation, past accuracy, and alignment with other reputable sources.

4. Language translation and localisation:

• Global reach: AI can translate news content into multiple languages, allowing news organisations to reach a wider audience and expand their global reach.
• Cultural sensitivity: AI can help journalists understand cultural nuances and tailor their content to specific audiences.

5. Accessibility and inclusion:

• Audio and video transcription: AI can automatically transcribe audio and video content, making it accessible to people with hearing impairments.
• Text-to-speech conversion: AI can convert text into speech, allowing people with visual impairments to consume news content.

While AI offers significant benefits to journalism, it is essential to use it responsibly and ethically.

Human journalists will continue to play a crucial role in ensuring the accuracy, objectivity, and quality of news content.

MHM: What are the dangers of using AI in journalism?

Gemini AI: While AI offers significant benefits to journalism, there are also potential dangers that must be addressed:

1. Bias and discrimination:

• Algorithmic bias: AI algorithms can perpetuate existing biases present in the data they are trained on. This can lead to biased news coverage and discrimination against certain groups.
• Lack of diversity: If the teams developing AI algorithms are not diverse, they may overlook biases that are relevant to underrepresented communities.

2. Misinformation and disinformation:

• Deepfakes and manipulated content: AI can be used to create deepfakes and other manipulated content that can spread misinformation and disinformation.
• Lack of fact-checking: Over-reliance on AI for fact-checking can lead to errors and the spread of false information.

3. Job displacement:

• Automation of tasks: AI can automate routine journalistic tasks, leading to job displacement and changes in the nature of journalism work.

4. Loss of human touch:

• Lack of empathy and nuance: AI may struggle to understand complex human emotions and nuances, leading to a loss of empathy and depth in news coverage.

5. Privacy concerns:

• Data collection and surveillance: The use of AI in journalism can involve the collection and analysis of large amounts of data, raising privacy concerns.

To mitigate these risks, it is essential to:

• Develop ethical guidelines: Establish clear ethical guidelines for the use of AI in journalism.
• Promote diversity and inclusion: Ensure that teams developing AI algorithms are diverse and inclusive.
• Invest in fact-checking and verification: Continue to invest in human fact-checkers and verification processes.
• Educate journalists: Provide journalists with training on how to use AI effectively and ethically.

By addressing these challenges, we can harness the power of AI to enhance journalism while minimising its risks.

MHM: You mention privacy concerns, isn’t that an issue with AI?

Gemini AI: You’re absolutely right. The use of AI to track user data, especially in the context of social media monitoring, can raise significant privacy concerns. Here are some of the main issues:

• Mass surveillance: Large-scale tracking of online activity can lead to a form of mass surveillance, where individuals feel constantly monitored.
• Data misuse: There’s a risk that collected data could be misused for purposes other than those stated, such as targeted advertising, profiling, or even surveillance by government agencies.
• Lack of transparency: Users may not be fully aware of the extent to which their data is being collected and used, leading to a lack of control and consent.

To mitigate these risks, it’s essential for news organisations and AI developers to:

• Obtain informed consent: Clearly communicate to users how their data will be collected, used, and stored.
• Implement strong privacy measures: Implement robust security measures to protect user data from unauthorised access.
• Limit data collection: Collect only the data necessary for the intended purpose and avoid excessive tracking.
• Be transparent about AI use: Disclose the use of AI tools and how they are used to process user data.
• Comply with data protection laws: Adhere to relevant data protection laws and regulations, such as GDPR in Europe and CCPA in California.

By addressing these concerns, news organisations can leverage AI for real-time event monitoring while respecting user privacy and building trust with their audience.

MHM: What role do journalists play in a newsroom using AI?

Gemini: In a newsroom utilising AI, journalists play a crucial role as human curators, analysts, and storytellers.

While AI can automate certain tasks like data analysis and content generation, it cannot fully replace the human judgement, creativity, and ethical considerations necessary for quality journalism.

Here’s a breakdown of the key roles journalists play:

• Human curators: Journalists select and prioritise the most important stories, ensuring that AI-generated content aligns with the newsroom’s values and editorial standards.
• Analysts and verifiers: Journalists use AI tools to analyse data and identify trends, but they also verify the accuracy and reliability of this information, ensuring that it is presented fairly and accurately.
• Storytellers: Journalists craft compelling narratives that resonate with audiences, adding context, nuance, and human perspective to AI-generated content.
• Ethical guardians: Journalists are responsible for ensuring that AI is used ethically and responsibly, avoiding biases and avoiding the spread of misinformation.

In essence, while AI can augment the capabilities of journalists, it cannot replace their unique abilities to identify significant stories, evaluate information critically, and communicate effectively with audiences.

MHM: What are the unique abilities that journalists possess that AI can’t replace?

Gemini AI: While AI can assist journalists in many tasks, it cannot fully replicate the following human abilities:

• Critical thinking and judgement: Journalists possess the ability to evaluate information critically, identify biases, and make informed judgments about the significance of events.
• Empathy and understanding: Journalists can understand the human experience, connect with sources, and tell stories that resonate with audiences on an emotional level.
• Creativity and storytelling: Journalists are skilled at crafting compelling narratives, using language effectively, and engaging readers with their writing.
• Ethical decision-making: Journalists must make ethical decisions about what to report, how to report it, and who to include or exclude from their stories.
• Adaptability and flexibility: Journalists must be able to adapt to rapidly changing situations, work under pressure, and meet deadlines.
• Cultural sensitivity and understanding: Journalists need to be aware of cultural nuances and avoid perpetuating stereotypes or biases.
• Building relationships: Journalists often rely on relationships with sources to obtain information and gain insights that AI cannot access.

While AI can assist with tasks like data analysis and content generation, it cannot fully replace the human judgement, creativity, and empathy that are essential for quality journalism.

MHM: Can a newsroom function without AI?

Gemini AI: Yes, a newsroom can function without AI. However, the efficiency and effectiveness of the newsroom’s operations may be significantly impacted.

AI can streamline many tasks, such as data analysis, content generation, and distribution, making the newsroom more efficient and productive.

Without AI, journalists would need to spend more time on tasks that can be automated, such as gathering and analysing data. This could lead to a slower news cycle and potentially reduce the depth and breadth of coverage.

Additionally, AI can help identify trends and patterns in data that may be difficult for humans to spot, providing valuable insights for journalists.

While AI is a valuable tool for newsrooms, it is not essential. Human journalists will always play a crucial role in ensuring the accuracy, objectivity, and quality of news content.

MHM: Could you set out a roadmap for the introduction of AI in a newsroom?

Gemini AI: Introducing AI into a newsroom requires careful planning and implementation. Here’s a suggested roadmap:

1. Assessment and planning

• Identify needs: Determine specific areas where AI can add value, such as data analysis, content generation, or distribution.
• Assess resources: Evaluate the availability of technical expertise, data, and budget.
• Develop goals: Set clear objectives for AI implementation, including improved efficiency, accuracy, or audience engagement.

2. Data preparation

• Gather data: Collect relevant data, such as news articles, social media posts, and audience analytics.
• Clean and prepare: Ensure data quality by cleaning, standardising, and structuring it for AI processing.

3. AI tool selection

• Evaluate tools: Research and compare AI tools that align with your needs and budget. Consider factors like scalability, ease of use, and integration capabilities.
• Pilot testing: Conduct pilot tests with selected tools to assess their performance and suitability.

4. Training and education

• Train staff: Provide training to journalists, editors, and other staff on how to use AI tools effectively.
• Address concerns: Address any concerns or resistance to AI adoption.

5. Integration and implementation

• Integrate tools: Integrate AI tools into existing workflows and systems.
• Start small: Begin with small-scale projects to gain experience and build confidence.
• Monitor and adjust: Continuously monitor the performance of AI tools and make adjustments as needed.

6. Ethical considerations

• Develop guidelines: Establish ethical guidelines for AI use, including bias mitigation, transparency, and accountability.
• Human oversight: Ensure that human journalists maintain oversight and control over AI-generated content.

7. Evaluation and refinement

• Measure impact: Assess the impact of AI on newsroom efficiency, accuracy, and audience engagement.
• Refine strategies: Continuously refine AI strategies based on evaluation results.

Main considerations:

• Human-AI collaboration: Emphasise the importance of human-AI collaboration, where AI complements human expertise rather than replacing it.
• Ethical use: Prioritise ethical considerations throughout the process, ensuring AI is used responsibly and transparently.
• Continuous learning: Stay updated on AI advancements and adapt your strategies accordingly.

By following this roadmap, newsrooms can successfully introduce AI while maintaining the highest standards of journalism.

MHM: How do you assess whether the introduction of AI in a newsroom has been successful?

Gemini AI: Evaluating the success of AI implementation in a newsroom requires a multifaceted approach. Here are some key metrics and considerations:

1. Efficiency and productivity:

• Time savings: Measure the reduction in time spent on manual tasks, such as data analysis and content generation.
• Increased output: Assess whether AI has enabled the production of more content or in-depth analysis.

2. Accuracy and quality:

• Error reduction: Evaluate if AI has helped reduce errors in reporting or fact-checking.
• Content quality: Assess the quality and relevance of AI-generated content, comparing it to human-generated content.

3. Audience engagement:

• Increased reach: Measure changes in audience reach and engagement metrics, such as website traffic, social media interactions, and email subscriptions.
• Audience feedback: Gather feedback from readers to understand their perception of AI-generated content.

4. Cost-effectiveness:

• ROI: Calculate the return on investment (ROI) by comparing the costs of AI implementation to the benefits, such as increased efficiency and revenue.
• Cost savings: Identify specific areas where AI has led to cost savings, such as reduced labour costs or improved resource utilisation.

5. Ethical considerations:

• Bias mitigation: Evaluate the effectiveness of measures to mitigate bias in AI algorithms and content.
• Transparency: Assess the level of transparency regarding AI use and its limitations.

6. Staff satisfaction:

• Morale: Measure staff satisfaction with the introduction of AI and its impact on their work.
• Skill development: Assess whether AI implementation has contributed to staff skill development and professional growth.

7. Adaptability and scalability:

• Flexibility: Evaluate the ability of AI tools to adapt to changing newsroom needs and priorities.
• Scalability: Assess the scalability of AI solutions to accommodate future growth and expansion.

By considering these factors, newsrooms can gain a comprehensive understanding of the success of their AI implementation and identify areas for improvement.

MHM: Can you give an example of a journalist using AI in the news gathering and production process?

Gemini AI: A journalist is covering a major political event, such as a presidential debate. They want to stay up-to-date with the latest developments and reactions from social media. They turn to AI Tool, a social media monitoring tool that can track mentions of specific keywords or hashtags in real-time.

Process:

• Set keywords: The journalist sets up the tool to monitor keywords related to the event, such as the names of the candidates, key topics, or relevant hashtags.
• Real-time monitoring: The tool tracks social media conversations in real-time, identifying mentions of the specified keywords.
• Identify trends: The journalist can analyse the data to identify trending topics, popular opinions, and potential breaking news stories.

Benefits:

• Faster reporting: The tool allows the journalist to quickly identify and report on important developments as they happen.
• Audience insights: By analysing social media conversations, the journalist can gain insights into public opinion and tailor their reporting accordingly.
• Efficiency: The tool can save time and effort by automating the process of monitoring social media.

By using AI for real-time event monitoring, journalists can stay informed about breaking news and provide their audience with timely and relevant coverage.

MHM: Can you suggest a user case scenario?

Gemini AI: A local news journalist is struggling to keep their audience engaged with generic news articles. They want to provide more personalised content that resonates with their readers.

The journalist uses an AI-powered content personalisation platform to analyse reader data, such as demographics, interests, and past behaviour. The platform then recommends relevant news stories and topics based on individual reader profiles.

Process:

• Data collection: The journalist collects data on their audience, such as email addresses, social media interactions, and website behaviour.
• AI analysis: The AI platform analyses this data to identify patterns and preferences among different reader segments.
• Content recommendations: Based on the analysis, the platform suggests personalised news stories and topics that are likely to interest each reader.
• Delivery: The journalist can then deliver this personalised content through email newsletters, social media, or their website.

Benefits:

• Increased engagement: Personalised content is more likely to capture the attention of readers, leading to increased engagement and loyalty.
• Targeted advertising: The platform can also help the journalist target advertising to specific reader segments, improving ad revenue.
• Data-driven insights: The AI platform provides valuable insights into audience behaviour, helping the journalist understand their readers better and tailor their content accordingly.

By using AI for personalised content, the journalist can create a more engaging and relevant experience for their audience, ultimately improving their news organisation’s success.

MHM: Can you sum up AI’s involvement in journalism in three pros and cons?

Gemini AI: Here are three pros and three cons about the use of AI in journalism.

Pros of AI in Journalism:

• Increased efficiency: AI can automate routine tasks, such as data analysis and content generation, freeing up journalists to focus on more in-depth and creative work.
• Enhanced accuracy: AI can help identify errors and inconsistencies in data, improving the accuracy of reporting.
• Personalised content: AI can tailor content to individual readers based on their preferences and interests, increasing audience engagement.

Cons of AI in Journalism:

• Bias and discrimination: AI algorithms can perpetuate existing biases present in the data they are trained on, leading to biased news coverage.
• Misinformation and disinformation: AI can be used to create deepfakes and other manipulated content that can spread misinformation.
• Job displacement: The automation of routine journalistic tasks can lead to job displacement and changes in the nature of journalism work.

MHM conclusion

This interview with Gemini AI suggests that artificial intelligence has an impressive ability to generate clear and useful copy. It is also able to be self-critical. It lists the potential risks of using AI in journalism, as well as the potential benefits. Perhaps the most important message is that AI recognises there are things it can’t do – functions that require human journalistic skill. AI can’t – yet – replace journalists in creating a news service. But it can, if used carefully, be a powerful tool in making that news coverage more attractive, interesting and comprehensive.

The post Hey AI, what can you do for journalism? first appeared on Media Helping Media.

The Documentary Film Academy has produced a free step-by-step guide for journalists who want to learn how to make documentaries.

In an introduction to the process, award-winning documentary filmmaker Sebastian Solberg has set out his 12 “essential steps” from researching the topic you want to cover to promoting the finished product.

The article below is taken from the Documentary Film Academy site and published here with Sebastian’s permission.

Documentary making – a step-by-step guide

Starting your journey in documentary filmmaking can often feel overwhelming. It can be challenging knowing where to start. So here are my 12 essential steps for making a documentary, filled with practical advice and insider tips to help you turn your idea into a compelling film.

You don’t have to be a professional to make a documentary film. In fact, I started out with no experience and a lot of questions. Since then I’ve gone on to create documentaries that have won awards, sparked social change, and attracted high-paying clients (you can check out my work here). And that’s why I founded the Documentary Film Academy in order to help beginners make their first documentary film.

1. Documentary Research

The best documentaries are the ones that come from a personal place. So, before anything else, you need to find a story idea that gets you excited and has interesting characters.

Do some initial research online and in your local libraries and bookstores to get an idea of what’s out there. But don’t just read about stories, watch them too. Not only will this give you a better understanding of the kinds of films that excite you, but you’ll also get some great ideas for your own project.

2. Choose a documentary narration style

There are many ways to categorise documentaries.

For example, film critic and theorist Bill Nichols categorised documentaries into six modes – poetic, expository, observational, participatory, reflexive and performative.

Nichols’ modes are written from an academic perspective and overlap narration style with subject matter and visual techniques. I think it is simpler to explain each of these elements separately.

So, instead, I have simplified Nichols’ modes down into four categories focussing purely on narration style as the distinguishing factor.

So, let’s get into it, here are the four main narration styles I use, when making a documentary:

Interview-led documentaries are based on interviews with the key people involved in the topic of the film. This type of documentary is typically used to explore a particular issue or event in depth.

Presenter-led documentaries are narrated by a presenter, who guides the viewer through the story. They can be used to tell any kind of story, from historical dramas to travel vlogs.

Observational-led documentaries are filmed entirely as if the viewer is an unseen observer, with no voiceover narration or interviews. This type of documentary is often used to capture reality in unscripted situations.

Narrator-led documentaries use a narrator to guide the viewer through the film, often providing additional information and insights that wouldn’t be possible in an observational or interview-led documentary.

It’s important to remember that often documentary films take elements from at least two, if not more of these styles. So when you’re looking for the best way to tell your story, don’t feel you’re limited to just one way of doing it.

Discover the pros and cons of each narration style here: Documentary Storytelling: Narration Style

3. Use a three-act documentary structure

Now that you have a good understanding of the documentary filmmaking process, it’s time to start thinking about your story. The best way to start is by using the Three-act Structure.

The Three-act Structure is a classic storytelling model that divides your documentary into three parts: Act 1 (Setup), Act 2 (Development), and Act 3 (Climax & Resolution). Each part has its own set of goals, which will help you map out the structure of your documentary.

For the beginning, your goal is to introduce your main characters and setting, and set up the conflict that will drive the rest of the film. In the middle, you’ll explore the conflict in more depth, and introduce new characters and subplots. And for the end, you’ll resolve the conflict and tie up all of the loose ends.

Dive deeper into documentary structure here: Master the Art of Documentary Storytelling in Three Acts

4. Find your documentary crew

Once you have your idea and equipment, the next step of documentary filmmaking for beginners is to find your team. You need to start assembling a group of like-minded individuals who are passionate about the topic you have chosen and can help make your project a success.

When looking for crew members, it’s important to consider what skills and insight they can bring to the project. Are you looking for an editor? A sound recordist? A cinematographer? All of these people play a key role in creating a successful documentary film.

Learn more about how to find your film crew here: How to Find a Film Crew to Help You Make Your Documentary

5. Create a documentary treatment

After you have thoroughly researched the topic of your documentary and gained a well-rounded understanding of it, you can then begin putting together a treatment.

Creating a treatment involves outlining the central focus and narrative of your documentary. It should include the main characters, key themes, what type of footage you want to capture, and any other information necessary to illustrate your vision.

A well-thought-out treatment is essential in helping you to organise your filming process, as it serves as an effective roadmap for when it comes time to begin shooting. It also gives potential crew members or collaborators an idea of what your documentary is going to look and feel like once it’s completed.

You can learn more about how to create a documentary treatment here: How to Create a Compelling Documentary Treatment

6. Create a documentary schedule & budget

With the research and planning phase complete, it’s time to create and stick to a schedule and budget. This is one of the most important steps in documentary filmmaking and sets the foundation for the rest of your project.

To put together your documentary schedule, break down each stage of production into manageable tasks that you can easily tackle in a set amount of time. Use any deadlines that are already in place as benchmarks, then plan out all necessary tasks from pre-production to post-production.

For creating your budget, consider things such as equipment rental, personnel costs, legal fees, travel expenses, etc. Make sure you add 10% of the total budget for any unexpected costs that may come up along the way. Having an estimated budget plan will help ensure you stay on track and on budget throughout production.

7. Choose camera equipment for your documentary

I’ve seen so many filmmakers starting out getting completely stressed out about what camera to buy to help them make their documentary and they hope it’s going to be a shortcut to improving their skills and validating themselves as a filmmaker.

But the truth is, and I’m sure you’ve heard this before, it’s far more important to master your skills as a filmmaker than invest in an expensive camera. So use whatever camera you have available to you, whether that a mobile phone or your friends Mirrorless camera.

8. Start shooting your documentary

Once you’ve finished your preparation, it’s time to start filming. As you film, be sure to get a variety of shots from different angles and distances. I like to use something called the five-shot rule to help with this:

1. So first up you’ll want to film a close-up of your subject’s hands to show what is being done.
2. Then film a close-up shot of your subject’s face.
3. Then a wide shot shows where the scene is taking place.
4. Then an over-the-shoulder shot of your subject.
5. And lastly, an unusual shot to show the scene unfolding – it’s up to you what camera angle you use. Just be creative with it, whether that means climbing up a tree to get a high angle, crawling on your belly to get a low angle or tilting your camera to get a dutch angle.

Using the five-shot rule will help you decide what angles to use when filming a scene, it’s especially useful if you have limited time to film. Once you’ve mastered the five-shot rule, you can add, subtract and mix up the angles you use when filming a scene and start to develop your own visual style.

Keep in mind that even if your footage isn’t perfect, don’t worry – that’s what editing is for. The goal here is just to capture enough material to make sure you can tell your story in the most compelling way possible.

9. Write a paper edit for your documentary

The next step in the documentary filmmaking process is to write a paper edit. This is the process of watching all of the footage you’ve shot and creating a paper edit. A paper edit is simply a written document that outlines the structure of your documentary film and includes notes about each scene. It’s also where you can make notes about transitions, music, and sound.

Writing a paper edit can be time-consuming but it’s an essential part of the filmmaking process. It will help you to stay organized and ensure that you have all of the footage you need for your documentary film before moving on to the editing stage.

10. Begin editing your documentary

Once you have all of your footage, it’s time to begin editing your documentary. This is where all the pieces and parts of your film come together to tell the story you want to tell. The process can be broken down into four steps: importing elements into the editing software, adding beats to the timeline, building the framework of your film, and refining and re-editing.

When you begin editing, start by importing all of your footage into your preferred editing software (I use Adobe Premiere Pro). Once your elements are inside, you’ll want to get familiar with each clip and start building an overall structure for the documentary. As you work through this step, consider where each beat should go using the three-act structure and what order they should be presented in to create a compelling story.

Once you have a basic framework built out onto the timeline, it’s time to refine and re-edit the film until it’s ready for its big debut!

Dive deeper into documentary editing: 6 Steps to Editing a Powerful Documentary

11. Colour grade, choose music & design soundscape for your documentary

The next step in the documentary filmmaking process is colour grading, music, and sound design. Once you’ve finished editing your film and have picture lock, it’s time to give your documentary its final touch.

Colour grading can make a huge difference in the look of your film by enhancing certain elements or creating a unique tone. With colour grading, you can manually adjust the colours of your video to give it a desired look and feel.

After colour grading comes music and sound design. You can find existing music or work with a composer to create a bespoke score for your documentary—and don’t forget about sound effects. Sound design is essential for setting the mood and creating an immersive experience. This could mean adding ambiance or creating sound effects from scratch.

12. Market & share your documentary film

When you have your documentary all finished and ready to go, the next step is to get it out there. You’ll want to start marketing your documentary using social media, email blasts and other forms of outreach. Generating buzz around your film is key to getting people interested in watching it.

Next, you should consider submitting your film to festivals or putting it online for people to watch. There are a few different options available when it comes to streaming services like Netflix, Amazon Prime or Vimeo, offering different levels of exposure and royalties. It all depends on what your end goal is with the film. Do you want as many people as possible to see it? Or do you want to make money from it? Knowing this will help you decide which distribution route is best for you.

Documentary Filmmaking Checklist

Making your first documentary can be tough with so much to do and plan. It’s easy to get lost and hard to know what to do next. That’s why I’ve created an easy-to-follow documentary filmmaking checklist. You can access it here: Documentary Filmmaking Checklist – after clicking that link you will be asked to submit your name and email address and the checklist will be sent to you.

The post How to make a documentary first appeared on Media Helping Media.

Fact-checking journalist Deepak Adhikari, the editor of Nepal Check, has shared a piece he wrote about the spread of AI-generated image following an earthquake in Nepal in November 2023. The article, below, explains how his organisation and others set about identifying the fake photographs. Deepak hopes the methods he and his team used will be of use to other journalists trying to combat the spread of fake images on social media and in other news output.

Social media is flooded with AI-generated images. Here’s how to detect them

By Deepak Adhikari, editor of Nepal Check

Following the devastating earthquake that struck Jajarkot district in Karnali Province in early November, social media users shared AI-generated images claiming to show the devastation caused.

One photograph showed dozens of houses ruined by the earthquake with people and rescuers walking through the debris. The photo was initially shared by Meme Nepal. It was subsequently used by celebrities, politicians and humanitarian organisations keen to draw attention to the disaster in one of Nepal’s poorest regions.

The image was used by Anil Keshary Shah, a former CEO of Nabil Bank and Rabindra Mishra, a senior vice president of National Democratic Party. (See archived version here and here)

When Nepal Check contacted Meme Nepal in an attempt to find the original source of the photo, they replied that they had found the image on social media.

A month on, the AI-generated images supposedly showing the aftermath of the earthquake continued. On December 14, 2023, Arjun Parajuli, a Nepali poet and founder of Pathshala Nepal, posted a photo claiming to show students studying in the ruins of the earthquake at Jajarkot. Parajuli. The poet attached the photo to a poem, had reshared the image from Manish Khadka, who identifies himself as a journalist based in Musikot of Rukum district.

Both these viral and poignant images were fake. They were generated using text-to-image generator platforms such as Midjourney, DALLE.

In the digital age it’s easy to manipulate images. With the rise of AI-enabled platforms it’s possible to generate images online quickly and convincingly. AI-generated images have evolved from amusingly odd to realistic. This has created further challenges for fact-checkers who are already inundated with misleading or false information circulating on social media platforms.

Fact-checkers often rely on Google’s Reverse Image Search, a tried and tested tool used to detect an image’s veracity. But Google and other search engines only show photos that have been previously published online.

So, how can one ascertain if an image is AI-generated? Currently, there is no tool that can determine this with 100% accuracy.

For example, Nepal Check used Illuminarty.ai and isitai.com to check the earthquake images to try to find out if they were generated using AI tools. After uploading an image to the platforms a percentage of how likely the image is to be generated by AI is shown.

Nepal Check contacted Kalim Ahmed, a former fact-checker at AltNews. He made the following observations about the image claiming to show devastation of the earthquake in Jajarkot.

• If you zoom in and take a closer look at the people they appear deformed and like toys.
  The rocks/debris just at the centre look like they’re straight out of a video game made in the late 90s or early 2000s.
• In the absence of a foolproof way to determine whether a photo is AI-generated, using observational skills and finding visual clues is the best way to tackle them.

A healthy dose of skepticism about what you see online (seeing is no longer believing), a search for the source of the content, whether there’s any evidence attached to the claim, and looking for context are powerful ways to separate fact from fiction online.

In a webinar in August this year organised by News Literacy Project, Dan Evon urged users to keep asking questions (is it authentic?). With the AI-images, their surfaces seem unusually smooth, which can be a giveaway, according to him. “Everything looks a little off,” he said.

Dan suggests looking for visual clues, adding that it was crucial to find out the provenance of the image. Experts caution that the virality of content on social media often stems from its ability to generate outrage or controversy, highlighting the need for careful consideration when encountering emotionally charged material.

In her comprehensive guide on detecting AI-generated images, Tamoa Calzadilla, a fellow at the Reynolds Journalism Institute in the US, encourages users to pay attention to hashtags that may indicate the use of AI in generating the content.

While AI has made significant progress in generating realistic images, it still faces challenges in accurately replicating human organs, such as eyes and hands. “That’s why it’s important to examine them closely: Do they have five fingers? Are all the contours clear? If they’re holding an object, are they doing so in a normal way?”, Tamoa writes in the guide.

Experts recommend that news media disclose information to readers and viewers regarding AI-generated images. Social media users are also advised to share the process publicly to mitigate the spread of misinformation.

Although the images purporting to depict the earthquake in Jajarkot lack a close-up view of the subjects, upon closer examination it becomes evident that they resemble drawings rather than real humans. Nepal Check also conducted a comparison between the viral AI-generated images and those disseminated by news media. We couldn’t find any such images that had been published on mainstream media in the aftermath of the earthquake.

The post How to detect AI-generated images first appeared on Media Helping Media.

Journalists can sometimes present an inaccurate or false version of events by making a simple common mistake. We either try too hard to ‘balance’ a story then end up distorting the facts, or we assess contributors or actors in our story as being roughly equal when in fact they are not.

This module looks at ways of avoiding two errors, applying ‘false equivalence’ and ‘false balance’.

These two errors, which are about making inaccurate comparisons, crop up frequently in journalism.

False equivalence is when you say that two or more things are the same, when in fact they are significantly different.

An example of false equivalence is to state that “politicians are all the same”. They are not. They might have similarities and some common attributes but that does not mean they are the same.

False balance is when a report suggests that two sides in a dispute have equally valid arguments, when in fact the evidence weighs heavily in favour of one side.

An example of false balance is the treatment of the climate change debate. Scientists come down heavily in favour of the proposition that human beings are causing, or at least helping to cause, global warming. A tiny minority, perhaps as low as three per cent, disagree, and it is false to represent the dispute as evenly-matched.

Ironically, many cases of false balance happen because the journalist is trying to avoid being biased.

When reporting a controversy, quite properly the journalist does not want to take sides.  But sometimes it is necessary to show that one side’s arguments and evidence are much more persuasive than the other side’s.

An example here is Donald Trump’s often-repeated claim that he won the 2020 US Presidential election. He has failed to produce any evidence to support that claim and has lost numerous court battles challenging the result. So it is false to present his claim as a viable argument.

False equivalence and false balance can both be used deliberately to mislead people. They are often used in misinformation and disinformation campaigns.

Or they can be examples of lazy thinking by the journalist.

Either way, they are inaccurate and care must be taken to avoid using them.

Things to remember in order to avoid using false equivalence and false balance:

• When you are tempted to say that two or more things are equal, ask yourself if you can justify the statement.
• If the comparison is likely to be controversial, explain why you think it is valid.
• Do not accept or repeat other people’s statements of equivalency, without testing their validity.
• When covering a dispute, make sure you reflect accurately all sides of the argument.  If some of the arguments are questionable, explain why.

It’s important to keep in mind that it is not biased to expose deficiencies in an argument, as long as you subject all sides to the same level of scrutiny.

Take a look at these other modules on Media Helping Media to help you keep your journalism up to the highest standards.

Unconscious bias and its impact on journalism

Impartiality in journalism

Accuracy in journalism

The post False equivalence and false balance first appeared on Media Helping Media.

Below are three excellent free training resources designed to help newsrooms “learn about the opportunities” and “support and grow all aspects of a news operation” by embracing AI.

They also include “writing guidelines for the role of AI in the newsroom.” The material has been produced by the AP, the LSE, and NiemanLab.

According to the AP, its course is “based on findings from AP’s research with local U.S. newsrooms and is designed for local news journalists and managers at all levels.”

The AP guide is designed to “Get your newsroom ready to incorporate technologies that include artificial intelligence to support and grow all aspects of your news operation.”

View the AP course.

In the first video in the AP’s course (link above), Jim Kennedy talks about how AP uses AI for “streamlining workflows and freeing journalists to focus on higher-order work” by “removing the grunt work that bogged down the news process every day”. Jim mentions how with some data-heavy journalism, such as sports stats and company financial results, content production increased tenfold.

The London School of Economics and Political Science (LSE) course is “a guide designed to help news organisations learn about the opportunities offered by AI to support their journalism”.

The LSE says its guide will help news organisation decide how to embrace AI journalism “to make your work more efficient and serve your audiences better”.

View the LSE’s guide.

The NiemanLab has produced “Writing guidelines for the role of AI in the newsroom.” It says the material sets out “the importance of meaningful human involvement and supervision in the use of AI, including through additional editing and factchecking of outputs before publication”.

View the NiemanLab suggested guidelines.

For more background on the development of AI and how it impacts news, you might want to view David Caswell’s presentation on “Generative AI and Automation of Media”.

David Caswell is the founder of StoryFlow Ltd., an innovation consultancy focused on AI workflows in news production. He was formerly an Executive Product Manager at BBC News Labs, focused on AI-based new product initiatives. He previously led product management for machine learning at Tribune Publishing and the Los Angeles Times, and was Director of Product Management for Automated Content Understanding at Yahoo!. David has also researched and published extensively on computational, structured and automated forms of journalism, including as a Fellow at the Reynolds Journalism Institute at the Missouri School of Journalism.

The post The role of AI in the newsroom first appeared on Media Helping Media.

Documentaries are in-depth stories told in a more interesting way. They can range in length from 10 minutes to an hour for one episode although sometimes they can stretch to a series or podcast. A great documentary engages listeners and puts them at the heart of the storytelling.

So, what elements make for a superior documentary?

First of all, the story you tell must be compelling enough to sustain telling at length. That means there must be a number of connected strands in it which must be examined and then tied up at the end.

There must be a significant increase in understanding on the part of listeners. The documentary will have shed light on an issue and offered a signpost to the way ahead.

A great documentary is based on sound research in order to construct the central thesis or argument. Good research involves exploring not just who might speak but also what they might say. It will explore all the aspects of a story even though some might lead to dead ends or blind alleys.

Every line of script in the documentary will need to be based on evidence. Every assertion made in the script must be based in reality and accuracy. Even when interviewees are making a point of view, their opinion must be backed by facts you can independently verify.

If your documentary is based on a theory which requires an answer from a relevant organisation or authority make sure that interview is the last in the sequence. That way you can make sure every relevant question can be put.

When you are recording natural sound or a reporter piece into the microphone make sure you record from the heart of the action, so listeners feel they are embedded in the item. So if you are recording a market scene, stand right next to the customer and the trader, not 15 metres away.

Unlike a radio feature, the documentary medium allows listeners to breathe and take in the atmosphere. You should aim for a roughly one third split between script, interviews, and sound effects (including music and natural sound).

Separate out your recordings into one folder for interviews, one for natural sound effects, and one for music. Listen through to all the interviews and select strong clips of your interviewees. Factual information can go into your script. The interview clip is where you can let your subjects speak powerfully and with emotion.

Arrange the clips in the order you would like them to appear in the programme. When you’ve identified the clips, start writing the script.

Use natural sound and music to create the mood and atmosphere.

The programme should flow along at a reasonable pace, but remember to give time for the listener to breathe in the atmosphere.

When you’ve assembled the script, clips, music and natural sound in the order you would like, try reading out the script in relation to everything else.

When you’re happy it works well together, record your voice pieces.

Enjoy making documentaries!

The post Making documentaries for radio first appeared on Media Helping Media.

We edit audio because we do not always have the time on air to broadcast a whole interview. Before you start editing audio, always ask the editor or producer of the item how long the edited item should be.

Make sure you are familiar with editing software you are using.

Ask whether you need to edit a cut down of the whole interview including your questions or if you are to provide one or more clips of just the interviewee talking.

Listen to the whole interview all the way through once, taking note of key points and noting down a time code for each important point made by the interviewee.

Listen out for poor quality. If you can’t hear what’s being said, it’s unlikely your listeners will be able to.

There are two main ways to edit – amputation and filleting.

Amputation implies cutting short the whole interview or cutting out whole questions and answers.

Filleting means taking only the essential parts of each answer and cutting out a little of each answer.

Amputation risks leaving out relevant information while filleting can result in an interview which sounds disjointed and unnatural.

Allow interviewees to sound as if they are having a conversation. It is not your job to make the interviewee sound more fluent or more polished.

However if they interject with hesitations such as ‘um’ and ‘er’ or leave long pauses in their answers, you should consider editing some of these out if it helps the listener understand what is being said.

Be careful not to cut all the hesitations and pauses out because that can sound artificial and unnatural.

Never take one answer and edit it as a response to another question. This is unethical and unprofessional.

Radio is a medium that is based on your ears. That mean when you edit audio, try not to edit using just the screen. Pay more attention to how it sounds rather than how it looks on the screen.

When you have finished editing, always listen back to the finished edit to make sure you have fulfilled the brief you were given, that you have captured all the relevant points the interviewee made, and that you have represented the interviewees points fairly and accurately.

The post Editing audio for radio news first appeared on Media Helping Media.